policy

CryptoOBPretraining

qhawkins · PyTorch

or hover any field below to flag it

Overview

Name
CryptoOBPretraining
Author
qhawkins
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
A high-performance framework for pre-training transformer models on cryptocurrency order book data using NVIDIA's Transformer Cores with FP8 precision. This project implements an end-to-end pipeline from raw market data processing to distributed transformer training. The pre-trained transformer serv

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

3+17 mentioned but not in catalog yet

Compatible environments

0

No environments list CryptoOBPretraining yet.

Datasets that reference this policy

0

No datasets reference CryptoOBPretraining yet.